EXMD 634

Course description:

This course is typically taught during the fall semester to graduate students in Experimental Medicine and other disciplines within the Faculty of Medicine at McGill University. It is an introductory statistics course with motivating examples will be drawn from both clinical research and basic science research. These methods are necessary for students to carry out their own research as well as to interpret research publications. This course serves as a foundation for more advanced courses in statistical modeling. The R statistical software environment and R Studio interface are used for computation.

Assessment:
Assessment will be based primarily on individual assignments. There will also be in-class mini-quizzes and a group project.

Suggested Reference:

  • Statistics for the life sciences, Myra Samuels, Jeffrey Wittmer and Andrew Schaffner, 5th edition, Pearson 2016 (student e-book available)

Course Schedule for EXMD 634 (2020):
Table 1
DATE TOPIC ASSIGNMENT
 September 2
(Lecture 1)
• Introduction to the course
• Sample size, precision, bias
• Random sampling and randomization
• Reporting guidelines
 
   • Introduction to R  
September 9
 (Lecture 2)
• Types of variables
• Types of observational units
• Types of study design
• Laws of probability
 

• Normal distribution
• Binomial distribution
• Random sampling and randomization
• Poisson or negative binomial distribution
 
September 16
(Lecture 3) 
 • Central limit theorem  Assignment
1 due
   • Confidence intervals for a single mean  
 September 23
(Lecture 4)
 • Confidence intervals for comparison of means
• Sample size calculation based on confidence intervals
 
   • Hypothesis testing for a single mean and for comparison of means
• Hypothesis testing vs Confidence intervals
 
 September 30
(Lecture 5)
 • Example problems involving t-tests for one or two sample means Assignment 2 due 
   • Sample size calculation based on hypothesis tests
(Type I vs. Type II errors)
 
October 7
(Lecture 6)
 • Bayesian inference for one or two means  
   • Probability of a wrong decision with hypothesis testing  
 October 14
(Lecture 7)
• Inference for a single proportion or comparison of two proportions: Confidence interval estimation
• Sample size calculations based on confidence intervals
• Inference for a single proportion or comparison of two proportions: Hypothesis testing
Assignment 3 due 
   • Sample size calculations based on hypothesis tests  
 October 21
(Lecture 8)
 • Hypothesis tests for contingency tables (Chi-squared test, Fisher’s exact test)  
 October 28
(Lecture 9)
• Nonparametric tests (sign test, Wilcoxon signed rank test, Wilcoxon rank sum test)
Bootstrap Confidence Intervals
 Assignment 4 due
 November 4
(Lecture 10)
• One-way ANOVA
• Null hypothesis and F-test
• Between- and within-groups variance
• Testing multiple comparisons
 
 November 11
(Lecture 11)
• Two-way ANOVA
• Randomized block design (or Repeated measures ANOVA)
• Correlation
 Assignment 5 due
 November 18
(Lecture 12)
• Simple linear regression: Model assumptions and estimation
• Multiple Linear regression with two predictors 
 
 November 25  Presentation of Course Project and submission of final course report  
 December 2    Assignment 6 due

Articles

Bayesian inference for HSROC diagnostic meta-analysis model

We pursue our series of blog articles illustrating rjags programs for diagnostic meta-analysis with an article describing how to carry out Bayesian inference for the...

Read more

Bayesian inference for the Bivariate model for diagnostic meta-analysis

Contents OVERVIEW MOTIVATING EXAMPLE AND DATA THE MODEL INITIAL VALUES COMPILING AND RUNNING THE MODEL MONITORING CONVERGENCE SUMMARY STATISTICS SROC plot SCRIPT...

Read more

Bayesian Sample Size Calculations for Difference in Proportions

Want to use a Bayesian approach to plan your study for comparing proportions? The R package SampleSizeProportions implements sample size calculations based on...

Read more

Learning rjags using simple statistical models

Here are some examples of fitting simple statistical models in rjags. They are useful for beginners learning Bayesian inference using the rjags library. Notice in...

Read more